Towards Goals in Informed Agent Negotiation
Negotiation is typically the way in which real world multi-issue commercial contracts are resolved and signed. The automation of negotiation in the B2B context has the potential to revolutionise trade. Intelligent agents have been proposed as the software architecture for automating negotiation. Goals are important based on the notion from  that an agent which focuses on negotiating by interests or goals rather than positions may increase the quality of agreement, and the speed of reaching the agreement. This paper presents work towards goal based negotiation that extends an information theoretical framework for automating negotiation using maximum entropy inference with linear information constraints. We place goals in terms of the information inference model, with a view towards goal based argumentation.
KeywordsIntelligent Agent Automate Negotiation Trading Agent Maximum Entropy Distribution Attribute Goal
Unable to display preview. Download preview PDF.
- 4.Debenham, J.: Bargaining with information. In: AAMAS 2004: Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 663–670. IEEE Computer Society, Los Alamitos (2004)Google Scholar
- 5.Debenham, J.: Auctions and bidding with information. In: AAMAS 2004: Agent Mediated Electronic Commerce Workshop AMEC within Third International Conference on Autonomous Agents and Multi Agent Systems, pp. 15–28. IEEE Computer Society, Los Alamitos (2004)Google Scholar